Improve model card for CheXPO-v2
#1
by
nielsr
HF Staff
- opened
This PR significantly enhances the model card for the CheXPO-v2 model by:
- Adding the
pipeline_tag: image-text-to-textfor better discoverability of this multimodal VLM. - Specifying
library_name: transformersto enable the "How to use" widget, as theconfig.jsonindicates compatibility with thetransformerslibrary (e.g.,transformers_version: "4.48.2",auto_mapentries forAutoConfig,AutoModelForCausalLM). - Including a link to the paper: CheXPO-v2: Preference Optimization for Chest X-ray VLMs with Knowledge Graph Consistency.
- Adding a direct link to the GitHub repository: https://github.com/ecoxial2007/CheX-Phi4MM.
- Providing a concise description of the model's purpose and key innovation.
Please review and merge these improvements.